ue5-blueprint-audio
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to run internal Python scripts, such asscripts/scan_project.pyandscripts/scrape_blueprint_api.py, which index project assets and build knowledge embeddings. These are internal vendor resources used for project indexing. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface due to its data ingestion capabilities.
- Ingestion points: The agent reads metadata, node information, and comments from Unreal Engine assets using the
scan_blueprintandlist_assetstools. - Boundary markers: Prompt templates lack explicit boundary markers or instructions to ignore instructions embedded in the scanned assets.
- Capability inventory: The agent has access to
Bash,Read, andGrep, which could be potentially misused if malicious instructions are ingested from asset files. - Sanitization: There is no evidence of sanitization or filtering applied to the asset data before it is incorporated into the agent's context.
Audit Metadata